import numpy as np 
import pandas as pd
import seaborn as sns
import matplotlib.pyplot as plt
import plotly.express as px
from warnings import filterwarnings 
filterwarnings("ignore")

data=pd.read_csv(r"C:\Users\laxma\Downloads\Fake News Detection Dataset.csv")

data.shape

(4500, 6)

data.head()

	ID	Word_Count	Number_of_Sentence	Unique_Words	Average_Word_Length	Label
0	1606	10	4	24	6.176750	1
1	3718	10	8	25	5.826770	1
2	2634	10	7	18	4.619040	1
3	5560	10	6	18	4.961424	1
4	7494	10	4	21	4.114324	1

data.tail()

	ID	Word_Count	Number_of_Sentence	Unique_Words	Average_Word_Length	Label
4495	1179	41	7	12	6.963924	0
4496	9445	100	5	15	3.136755	1
4497	4149	100	8	18	3.376823	1
4498	9877	85	14	42	5.331393	0
4499	6709	57	6	7	4.312751	0

data.isnull().sum()

ID                     0
Word_Count             0
Number_of_Sentence     0
Unique_Words           0
Average_Word_Length    0
Label                  0
dtype: int64

data.duplicated().sum()

0

data.describe()

	ID	Word_Count	Number_of_Sentence	Unique_Words	Average_Word_Length	Label
count	4500.000000	4500.000000	4500.000000	4500.000000	4500.000000	4500.000000
mean	5469.140000	53.934000	8.934667	24.943333	4.968105	0.329556
std	2599.193059	24.872743	3.407847	11.540708	1.152394	0.470104
min	1002.000000	10.000000	4.000000	5.000000	3.000385	0.000000
25%	3228.750000	35.000000	6.000000	17.000000	3.980553	0.000000
50%	5449.500000	52.000000	9.000000	22.000000	4.906200	0.000000
75%	7706.750000	75.000000	12.000000	33.000000	5.996111	1.000000
max	9999.000000	100.000000	15.000000	50.000000	6.999799	1.000000

data.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 4500 entries, 0 to 4499
Data columns (total 6 columns):
 #   Column               Non-Null Count  Dtype  
---  ------               --------------  -----  
 0   ID                   4500 non-null   int64  
 1   Word_Count           4500 non-null   int64  
 2   Number_of_Sentence   4500 non-null   int64  
 3   Unique_Words         4500 non-null   int64  
 4   Average_Word_Length  4500 non-null   float64
 5   Label                4500 non-null   int64  
dtypes: float64(1), int64(5)
memory usage: 211.1 KB

data.columns

Index(['ID', 'Word_Count', 'Number_of_Sentence', 'Unique_Words',
       'Average_Word_Length', 'Label'],
      dtype='object')

#VISUALIZATION

plt.scatter(data['ID'],data['Number_of_Sentence'],color='yellowgreen')
plt.xticks(rotation=90)
plt.show()

fig=px.violin(data,x='Word_Count',y='Unique_Words',color='Word_Count')
fig.show()

plt.bar(data['Label'],data['ID'])
plt.xticks(rotation=90)
plt.show()

plt.figure(figsize=(10,4))
sns.countplot(x='Word_Count', data=data, color='b')
plt.xticks(rotation=90)
plt.show()

plt.figure(figsize=(10,4))
top_car = data['Label'].value_counts().nlargest(10)
sns.countplot(y=data.Label,color='red')

<AxesSubplot:xlabel='count', ylabel='Label'>

plt.figure(figsize=(8, 4))
sns.scatterplot(data=data, x='Label', y='Word_Count')
plt.xlabel('Label')
plt.ylabel('Word_Count')
plt.show()

sns.barplot(data['Unique_Words'],data['Average_Word_Length'],color='cyan')
plt.xticks(rotation=90)
plt.show()

sns.displot(data["Label"])

<seaborn.axisgrid.FacetGrid at 0x17cc89784c0>

sns.lineplot(x='Number_of_Sentence', y='Label', data=data)

<AxesSubplot:xlabel='Number_of_Sentence', ylabel='Label'>

sns.countplot(x='Unique_Words',data=data)

<AxesSubplot:xlabel='Unique_Words', ylabel='count'>

#MODEL BUILDING

y = data["Word_Count"].values
x_data=data.drop(["Word_Count"],axis=1)
x = (x_data-np.min(x_data))/(np.max(x_data)-np.min(x_data))
from sklearn.model_selection import train_test_split
x_train, x_test, y_train, y_test = train_test_split(x,y,test_size = 0.2,random_state=1)

from sklearn.svm import SVC
svm=SVC(random_state=1)
svm.fit(x_train,y_train)
print("train accuracy:",svm.score(x_train,y_train))
print("test accuracy:",svm.score(x_test,y_test))

train accuracy: 0.08583333333333333
test accuracy: 0.05333333333333334